Training Data Sensitivity Analysis of Deep Neural Network for Differentiating Construction Laborers with/without Safety Helmets
Publication: Computing in Civil Engineering 2023
ABSTRACT
Deep learning-based detection of construction workers wearing or not wearing safety helmets has gained popularity in both research and commercial domains. However, most of the datasets used for training have been created without considering the contextual consistency of construction sites. To address this issue, this study compiled a new SCSI (Safety Construction Site Image) dataset that is suitable for construction environments. The dataset consists of 15,551 images distinguished by two classes, “person with helmet” and “person without helmet,” for similar construction features such as tunnels, commercial buildings, earth works, and others. For validation, YOLOv5s and YOLOv8n were used to confirm the performance of different combinations of datasets with SHEL5K. As a result of training, our dataset produced better results than the SHEL5K dataset in the various construction environments noted above. These results serve to emphasize the importance of creating datasets with consistent image contexts.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Berrar, D. (2019). Cross-Validation.
Chen, H., Xiong, F., Wu, D., Zheng, L., Peng, A., Hong, X., Tang, B., Lu, H., Shi, H., and Zheng, H. (2017, November). Assessing impacts of data volume and data set balance in using deep learning approach to human activity recognition. In 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1160–1165). IEEE.
Chen, Y., Li, W., Sakaridis, C., Dai, D., and Van Gool, L. (2018). In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3339–3348).
Chen, Z., Ting, D., Newbury, R., and Chen, C. (2021). Semantic segmentation for partially occluded apple trees based on deep learning. Computers and Electronics in Agriculture, 181, 105952.
Farahani, A., Voghoei, S., Rasheed, K., and Arabnia, H. R. (2021). A brief review of domain adaptation. Advances in Data Science and Information Engineering: Proceedings from ICDATA 2020 and IKE 2020, 877–894.
Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580–587).
Guan, H., and Liu, M. (2021). Domain adaptation for medical image analysis: a survey. IEEE Transactions on Biomedical Engineering, 69(3), 1173–1185.
Hayat, A., and Morgado-Dias, F. (2022). Deep learning-based automatic safety helmet detection system for construction safety. Applied Sciences, 12(16), 8268.
Hsu, H. K., Yao, C. H., Tsai, Y. H., Hung, W. C., Tseng, H. Y., Singh, M., and Yang, M. H. (2020). Progressive domain adaptation for object detection. In Proceedings of the IEEE/CVF winter conference on applications of computer vision (pp. 749–757).
Huang, Z., Yang, S., Zhou, M., Gong, Z., Abusorrah, A., Lin, C., and Huang, Z. (2022). Making accurate object detection at the edge: review and new approach. Artificial Intelligence Review, 55(3), 2245–2274.
Jocher, G. (2020). YOLOv5 by Ultralytics (Version 7.0) [Computer software]. https://doi.org/10.5281/zenodo.3908559.
Jocher, G., Chaurasia, A., and Qiu, J. (2023). YOLO by Ultralytics (Version 8.0.0) [Computer software]. https://github.com/ultralytics/ultralytics.
Kim, H., Kim, H., Hong, Y. W., and Byun, H. (2018). Detecting construction equipment using a region-based fully convolutional network and transfer learning. Journal of computing in Civil Engineering, 32(2), 04017082.
Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117–2125).
Lin, T. Y., Goyal, P., Girshick, R., He, K., and Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980–2988).
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., and Berg, A. C. (2016). Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14 (pp. 21–37). Springer International Publishing.
Lu, S., Wang, B., Wang, H., Chen, L., Linjian, M., and Zhang, X. (2019). A real-time object detection algorithm for video. Computers & Electrical Engineering, 77, 398–408.
Ma, J. W., Czerniawski, T., and Leite, F. (2020). Semantic segmentation of point clouds of building interiors with deep learning: Augmenting training datasets with synthetic BIM-based point clouds. Automation in Construction, 113, 103144.
NIS (National Information Society Agency). AIHUB. (accessed on 14 Mar 2023); https://aihub.or.kr/.
Otgonbold, M. E., Gochoo, M., Alnajjar, F., Ali, L., Tan, T. H., Hsieh, J. W., and Chen, P. Y. (2022). SHEL5K: An extended dataset and benchmarking for safety helmet detection. Sensors, 22(6), 2315.
Oza, P., Sindagi, V. A., Sharmini, V. V., and Patel, V. M. (2023). Unsupervised domain adaptation of object detectors: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence.
Padilla, R., Netto, S. L., and Da Silva, E. A. (2020, July). A survey on performance metrics for object-detection algorithms. In 2020 international conference on systems, signals and image processing (IWSSIP) (pp. 237–242). IEEE.
Park, S., Yoon, S., and Heo, J. (2019). Image-based automatic detection of construction helmets using R-FCN and transfer learning. KSCE Journal of Civil and Environmental Engineering Research, 39(3), 399–407.
Purkait, P., Zach, C., and Reid, I. (2019, November). Seeing behind things: Extending semantic segmentation to occluded regions. In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 1998–2005). IEEE.
Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779–788).
Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, X., Li, J., and Sun, J. (2019). Objects365: A large-scale, high-quality dataset for object detection. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 8430–8439).
Shorten, C., and Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of big data, 6(1), 1–48.
Tzutalin. LabelImg. Git code (2015). https://github.com/tzutalin/labelImg.
Zhao, Z. Q., Zheng, P., Xu, S. T., and Wu, X. (2019). Object detection with deep learning: A review. IEEE transactions on neural networks and learning systems, 30(11), 3212–3232.
Zhou, F., Zhao, H., and Nie, Z. (2021, January). Safety helmet detection based on YOLOv5. In 2021 IEEE International conference on power electronics, computer applications (ICPECA) (pp. 6–11). IEEE.
Information & Authors
Information
Published In
Computing in Civil Engineering 2023
Pages: 516 - 524
History
Published online: Jan 25, 2024
ASCE Technical Topics:
- Analysis (by type)
- Business management
- Construction engineering
- Construction management
- Construction sites
- Data analysis
- Education
- Employment
- Engineering fundamentals
- Labor
- Methodology (by type)
- Network analysis
- Occupational safety
- Personnel management
- Practice and Profession
- Public administration
- Public health and safety
- Research methods (by type)
- Safety
- Sensitivity analysis
- Training
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.